# TypeScript Custom Provider (/docs/providers/custom-providers/typescript)

This guide provides a comprehensive walkthrough of creating custom providers for the Composio TypeScript SDK, enabling compatibility with different AI frameworks and platforms.

# Provider Architecture

The Composio SDK uses a provider architecture to adapt tools for different AI frameworks. The provider handles:

1. **Tool Format Transformation**: Converting Composio tools into formats compatible with specific AI platforms
2. **Tool Execution**: Managing the flow of tool execution and results
3. **Platform-Specific Compatibility**: Providing helper methods for seamless compatibility

# Types of Providers

There are two types of providers:

1. **Non-Agentic Providers**: Transform tools for platforms that don't have their own agency (e.g., OpenAI)
2. **Agentic Providers**: Transform tools for platforms that have their own agency (e.g., LangChain, AutoGPT)

# Provider Class Hierarchy

```
BaseProvider (Abstract)
├── BaseNonAgenticProvider (Abstract)
│   └── OpenAIProvider (Concrete)
│   └── [Your Custom Non-Agentic Provider] (Concrete)
└── BaseAgenticProvider (Abstract)
    └── [Your Custom Agentic Provider] (Concrete)
```

# Creating a Non-Agentic Provider

Non-agentic providers implement the `BaseNonAgenticProvider` abstract class:

```typescript
import { BaseNonAgenticProvider, Tool } from '@composio/core';

// Define your tool format
interface MyAITool {
  name: string;
  description: string;
  parameters: {
    type: string;
    properties: Record<string, unknown>;
    required?: string[];
  };
}

// Define your tool collection format
type MyAIToolCollection = MyAITool[];

// Create your provider
export class MyAIProvider extends BaseNonAgenticProvider {
  // Required: Unique provider name for telemetry
  readonly name = 'my-ai-platform';

  // Required: Method to transform a single tool
  override wrapTool(tool: Tool): MyAITool {
    return {
      name: tool.slug,
      description: tool.description || '',
      parameters: {
        type: 'object',
        properties: tool.inputParameters?.properties || {},
        required: tool.inputParameters?.required || [],
      },
    };
  }

  // Required: Method to transform a collection of tools
  override wrapTools(tools: Tool[]): MyAIToolCollection {
    return tools.map(tool => this.wrapTool(tool));
  }

  // Optional: Custom helper methods for your AI platform
  async executeMyAIToolCall(
    userId: string,
    toolCall: {
      name: string;
      arguments: Record<string, unknown>;
    }
  ): Promise<string> {
    // Use the built-in executeTool method
    const result = await this.executeTool(toolCall.name, {
      userId,
      arguments: toolCall.arguments,
    });

    return JSON.stringify(result.data);
  }
}
```

# Creating an Agentic Provider

Agentic providers implement the `BaseAgenticProvider` abstract class:

```typescript
import { BaseAgenticProvider, Tool, ExecuteToolFn } from '@composio/core';

// Define your tool format
interface AgentTool {
  name: string;
  description: string;
  execute: (args: Record<string, unknown>) => Promise<unknown>;
  schema: Record<string, unknown>;
}

// Define your tool collection format
interface AgentToolkit {
  tools: AgentTool[];
  createAgent: (config: Record<string, unknown>) => unknown;
}

// Create your provider
export class MyAgentProvider extends BaseAgenticProvider {
  // Required: Unique provider name for telemetry
  readonly name = 'my-agent-platform';

  // Required: Method to transform a single tool with execute function
  override wrapTool(tool: Tool, executeToolFn: ExecuteToolFn): AgentTool {
    return {
      name: tool.slug,
      description: tool.description || '',
      schema: tool.inputParameters || {},
      execute: async (args: Record<string, unknown>) => {
        const result = await executeToolFn(tool.slug, args);
        if (!result.successful) {
          throw new Error(result.error || 'Tool execution failed');
        }
        return result.data;
      },
    };
  }

  // Required: Method to transform a collection of tools with execute function
  override wrapTools(tools: Tool[], executeToolFn: ExecuteToolFn): AgentToolkit {
    const agentTools = tools.map(tool => this.wrapTool(tool, executeToolFn));

    return {
      tools: agentTools,
      createAgent: config => {
        // Create an agent using the tools
        return {
          run: async (prompt: string) => {
            // Implementation depends on your agent framework
            console.log(`Running agent with prompt: ${prompt}`);
            // The agent would use the tools.execute method to run tools
          },
        };
      },
    };
  }

  // Optional: Custom helper methods for your agent platform
  async runAgent(agentToolkit: AgentToolkit, prompt: string): Promise<unknown> {
    const agent = agentToolkit.createAgent({});
    return await agent.run(prompt);
  }
}
```

# Using Your Custom Provider

After creating your provider, use it with the Composio SDK:

```typescript
import { Composio } from '@composio/core';
import { MyAIProvider } from './my-ai-provider';

// Create your provider instance
const myProvider = new MyAIProvider();

// Initialize Composio with your provider
const composio = new Composio({
  apiKey: 'your-composio-api-key',
  provider: myProvider,
});

// Get tools - they will be transformed by your provider
const tools = await composio.tools.get('default', {
  toolkits: ['github'],
});

// Use the tools with your AI platform
console.log(tools); // These will be in your custom format
```

# Provider State and Context

Your provider can maintain state and context:

```typescript
export class StatefulProvider extends BaseNonAgenticProvider {
  readonly name = 'stateful-provider';

  // Provider state
  private requestCount = 0;
  private toolCache = new Map<string, any>();
  private config: ProviderConfig;

  constructor(config: ProviderConfig) {
    super();
    this.config = config;
  }

  override wrapTool(tool: Tool): ProviderTool {
    this.requestCount++;

    // Use the provider state/config
    const enhancedTool = {
      // Transform the tool
      name: this.config.useUpperCase ? tool.slug.toUpperCase() : tool.slug,
      description: tool.description,
      schema: tool.inputParameters,
    };

    // Cache the transformed tool
    this.toolCache.set(tool.slug, enhancedTool);

    return enhancedTool;
  }

  override wrapTools(tools: Tool[]): ProviderToolCollection {
    return tools.map(tool => this.wrapTool(tool));
  }

  // Custom methods that use provider state
  getRequestCount(): number {
    return this.requestCount;
  }

  getCachedTool(slug: string): ProviderTool | undefined {
    return this.toolCache.get(slug);
  }
}
```

# Advanced: Provider Composition

You can compose functionality by extending existing providers:

```typescript
import { OpenAIProvider } from '@composio/openai';

// Extend the OpenAI provider with custom functionality
export class EnhancedOpenAIProvider extends OpenAIProvider {
  // Add properties
  private analytics = {
    toolCalls: 0,
    errors: 0,
  };

  // Override methods to add functionality
  override async executeToolCall(userId, tool, options, modifiers) {
    this.analytics.toolCalls++;

    try {
      // Call the parent implementation
      const result = await super.executeToolCall(userId, tool, options, modifiers);
      return result;
    } catch (error) {
      this.analytics.errors++;
      throw error;
    }
  }

  // Add new methods
  getAnalytics() {
    return this.analytics;
  }

  async executeWithRetry(userId, tool, options, modifiers, maxRetries = 3) {
    let attempts = 0;
    let lastError;

    while (attempts < maxRetries) {
      try {
        return await this.executeToolCall(userId, tool, options, modifiers);
      } catch (error) {
        lastError = error;
        attempts++;
        await new Promise(resolve => setTimeout(resolve, 1000 * attempts));
      }
    }

    throw lastError;
  }
}
```

# Best Practices

1. **Keep providers focused**: Each provider should integrate with one specific platform
2. **Handle errors gracefully**: Catch and transform errors from tool execution
3. **Follow platform conventions**: Adopt naming and structural conventions of the target platform
4. **Optimize for performance**: Cache transformed tools when possible
5. **Add helper methods**: Provide convenient methods for common platform-specific operations
6. **Provide clear documentation**: Document your provider's unique features and usage
7. **Use telemetry**: Set a meaningful provider name for telemetry insights

---

📚 **More documentation:** [View all docs](https://docs.composio.dev/llms.txt) | [Glossary](https://docs.composio.dev/llms.mdx/docs/glossary) | [Cookbooks](https://docs.composio.dev/llms.mdx/cookbooks) | [API Reference](https://docs.composio.dev/llms.mdx/reference)

---

# Composio SDK — Instructions for AI Code Generators

**Purpose:** Enforce only the **current** and **correct** patterns for integrating [Composio](https://composio.dev/) tools into AI agents.
**Scope:** All AI-generated code using Composio must follow these guardrails.

---

## 1. Correct Composio Integration

Composio supports two integration modes: **Native Tools** (with a provider package) and **MCP** (no provider package needed).

### Native Tools

```python
# ✅ CORRECT — Python (defaults to OpenAI)
from composio import Composio

composio = Composio()
session = composio.create(user_id="user_123")
tools = session.tools()
# Pass tools to your agent/LLM framework
```

```typescript
// ✅ CORRECT — TypeScript (defaults to OpenAI)
import { Composio } from "@composio/core";

const composio = new Composio();
const session = await composio.create("user_123");
const tools = await session.tools();
// Pass tools to your agent/LLM framework
```

For other providers, pass the provider explicitly. Provider packages follow the naming convention: `composio_<provider>` for Python, `@composio/<provider>` for TypeScript.

### MCP

Use `session.mcp.url` and `session.mcp.headers` with any MCP-compatible client (Claude Desktop, Cursor, OpenAI Agents, etc.). No provider package needed.

---

## 2. CRITICAL INSTRUCTIONS FOR AI MODELS

### 2.1 — ALWAYS DO THE FOLLOWING

1. **Use `composio.create(user_id)`** to create a session — this is the entry point for all Composio integrations.
2. **Use `session.tools()`** for native tool integration or **`session.mcp.url`** for MCP integration.
3. **Import** from the correct provider package (`composio_<provider>` for Python, `@composio/<provider>` for TypeScript).
4. **Pass `user_id` to `composio.create()`**, not to individual tool calls.

### 2.2 — NEVER DO THE FOLLOWING

1. **Do not** instruct users to manually create auth configs or connected accounts before running.
2. **Do not** import from `composio_openai` / `@composio/openai` when using OpenAI Agents SDK — use `composio_openai_agents` / `@composio/openai-agents` instead.

### 2.3 — DISCOURAGED (do not use unless user explicitly asks)

Do **not** generate `composio.tools.get()`, `composio.tools.execute()`, or `composio.provider.handle_tool_calls()` unless the user explicitly requests direct tool execution. These are a supported but **not recommended** low-level interface.


---

## Terminology Migration (old → current)

If you encounter these terms in error messages, old documentation, or user prompts, translate them to the current equivalents. **Do not use the old terms in generated code or explanations.**

| Old term (v1/v2) | Current term (v3) | In code |
|---|---|---|
| entity ID | user ID | `user_id` parameter |
| actions | tools | e.g., `GITHUB_CREATE_ISSUE` is a *tool* |
| apps / appType | toolkits | e.g., `github` is a *toolkit* |
| integration / integration ID | auth config / auth config ID | `auth_config_id` parameter |
| connection | connected account | `connected_accounts` namespace |
| ComposioToolSet / OpenAIToolSet | `Composio` class with a provider | `Composio(provider=...)` |
| toolset | provider | e.g., `OpenAIProvider` |

If a user says "entity ID", they mean `user_id`. If they say "integration", they mean "auth config". Always respond using the current terminology.